Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1424 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0649. Min Act: -0.0002

Data Index: 288796 (C4 (Web Text))

Max Activating Token Index: 628

Text #1

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0616. Min Act: -0.0002

Data Index: 495328 (C4 (Web Text))

Max Activating Token Index: 331

Text #2

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0609. Min Act: -0.0002

Data Index: 899336 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0604. Min Act: -0.0001

Data Index: 189386 (C4 (Web Text))

Max Activating Token Index: 28

Text #4

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0598. Min Act: -0.0002

Data Index: 731017 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0595. Min Act: -0.0001

Data Index: 159196 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0568. Min Act: -0.0001

Data Index: 120427 (C4 (Web Text))

Max Activating Token Index: 922

Text #7

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0552. Min Act: -0.0002

Data Index: 257903 (C4 (Web Text))

Max Activating Token Index: 611

Text #8

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0561. Min Act: -0.0002

Data Index: 1024719 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0542. Min Act: -0.0001

Data Index: 20453 (C4 (Web Text))

Max Activating Token Index: 49

Text #10

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0558. Min Act: -0.0002

Data Index: 835399 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0518. Min Act: -0.0002

Data Index: 36818 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1108769 (C4 (Web Text))

Max Activating Token Index: 764

Text #13

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0547. Min Act: -0.0002

Data Index: 681854 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0521. Min Act: 0.0001

Data Index: 588268 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0547. Min Act: -0.0002

Data Index: 777287 (C4 (Web Text))

Max Activating Token Index: 802

Text #16

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0517. Min Act: -0.0002

Data Index: 156346 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0519. Min Act: -0.0002

Data Index: 991171 (C4 (Web Text))

Max Activating Token Index: 627

Text #18

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0521. Min Act: -0.0002

Data Index: 801816 (C4 (Web Text))

Max Activating Token Index: 680

Text #19

Max Range: 0.0649. Min Range: -0.0649

Max Act: 0.0535. Min Act: -0.0002

Data Index: 470346 (C4 (Web Text))

Max Activating Token Index: 943